Related papers: Augmented World Models Facilitate Zero-Shot Dynami…
The ability to predict future outcomes given control actions is fundamental for physical reasoning. However, such predictive models, often called world models, remains challenging to learn and are typically developed for task-specific…
Imitation learning has emerged as a promising approach towards building generalist robots. However, scaling imitation learning for large robot foundation models remains challenging due to its reliance on high-quality expert demonstrations.…
Training robot policies within a learned world model is trending due to the inefficiency of real-world interactions. The established image-based world models and policies have shown prior success, but lack robust geometric information that…
A World Model is a compressed spatial and temporal representation of a real world environment that allows one to train an agent or execute planning methods. However, world models are typically trained on observations from the real world…
Much of model-based reinforcement learning involves learning a model of an agent's world, and training an agent to leverage this model to perform a task more efficiently. While these models are demonstrably useful for agents, every…
We use model-free reinforcement learning, extensive simulation, and transfer learning to develop a continuous control algorithm that has good zero-shot performance in a real physical environment. We train a simulated agent to act optimally…
Designing adaptive mechanisms to align individual and collective interests remains a central challenge in artificial social intelligence. Existing methods often struggle with modeling heterogeneous agents possessing persistent latent traits…
To interact effectively with humans in the real world, it is important for agents to understand language that describes the dynamics of the environment--that is, how the environment behaves--rather than just task instructions specifying…
The robustness of any machine learning solution is fundamentally bound by the data it was trained on. One way to generalize beyond the original training is through human-informed augmentation of the original dataset; however, it is…
World models promise a paradigm shift in robotics, where an agent learns the underlying physics of its environment once to enable efficient planning and behavior learning. However, current world models are often hardware-locked specialists:…
Offline reinforcement learning leverages pre-collected datasets of transitions to train policies. It can serve as effective initialization for online algorithms, enhancing sample efficiency and speeding up convergence. However, when such…
A world model creates a surrogate world to train a controller and predict safety violations by learning the internal dynamic model of systems. However, the existing world models rely solely on statistical learning of how observations change…
Learning robust and generalizable world models is crucial for enabling efficient and scalable robotic control in real-world environments. In this work, we introduce a novel framework for learning world models that accurately capture…
Reinforcement Learning (RL) has made significant strides in complex tasks but struggles in multi-task settings with different embodiments. World model methods offer scalability by learning a simulation of the environment but often rely on…
Large language models (LLMs) have recently gained much attention in building autonomous agents. However, the performance of current LLM-based web agents in long-horizon tasks is far from optimal, often yielding errors such as repeatedly…
Model-based offline optimization with dynamics-aware policy provides a new perspective for policy learning and out-of-distribution generalization, where the learned policy could adapt to different dynamics enumerated at the training stage.…
This work focuses on enhancing the generalization performance of deep reinforcement learning-based robot navigation in unseen environments. We present a novel data augmentation approach called scenario augmentation, which enables robots to…
Zero-shot generalization (ZSG) to unseen dynamics is a major challenge for creating generally capable embodied agents. To address the broader challenge, we start with the simpler setting of contextual reinforcement learning (cRL), assuming…
We consider the problem of learning useful robotic skills from previously collected offline data without access to manually specified rewards or additional online exploration, a setting that is becoming increasingly important for scaling…
While reinforcement learning has achieved remarkable successes in several domains, its real-world application is limited due to many methods failing to generalise to unfamiliar conditions. In this work, we consider the problem of…